LovenOO's picture
update model card README.md
b090959
metadata
license: apache-2.0
base_model: distilbert-base-uncased
tags:
  - generated_from_trainer
metrics:
  - precision
  - recall
  - f1
  - accuracy
model-index:
  - name: distilBERT_mergeddata_with_preprocessing_grid_search
    results: []

distilBERT_mergeddata_with_preprocessing_grid_search

This model is a fine-tuned version of distilbert-base-uncased on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 0.1742
  • Precision: 0.9650
  • Recall: 0.9650
  • F1: 0.9648
  • Accuracy: 0.965

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

  • learning_rate: 2e-05
  • train_batch_size: 32
  • eval_batch_size: 32
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 10

Training results

Training Loss Epoch Step Validation Loss Precision Recall F1 Accuracy
No log 1.0 225 0.2068 0.9550 0.9536 0.9537 0.9544
No log 2.0 450 0.1497 0.9583 0.9585 0.9582 0.9583
0.445 3.0 675 0.1408 0.9628 0.9631 0.9627 0.9628
0.445 4.0 900 0.1484 0.9630 0.9630 0.9626 0.9628
0.0585 5.0 1125 0.1487 0.9675 0.9680 0.9676 0.9678
0.0585 6.0 1350 0.1538 0.9665 0.9670 0.9665 0.9667
0.0242 7.0 1575 0.1666 0.9644 0.9645 0.9642 0.9644
0.0242 8.0 1800 0.1709 0.9672 0.9673 0.9671 0.9672
0.0111 9.0 2025 0.1707 0.9670 0.9672 0.9670 0.9672
0.0111 10.0 2250 0.1742 0.9650 0.9650 0.9648 0.965

Framework versions

  • Transformers 4.31.0
  • Pytorch 2.0.1+cu118
  • Datasets 2.14.4
  • Tokenizers 0.13.3